A computer-implemented method for knowledge based ontology editing, is provided. The method receives a language instance to update a knowledge base, using a computer. The method semantically parses the language instance to detect an ontology for editing. The method maps one or more nodes for the ontology for editing based on an ontology database and the knowledge base. The method determines whether the mapped nodes are defined or undefined within the knowledge base. The method calculates a first confidence score based on a number of the defined and undefined mapped nodes. Furthermore, the method updates the knowledge base when the first confidence score meets a pre-defined threshold.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method for knowledge based ontology editing, comprising: receiving a language instance to update a knowledge base, using a computer; semantically parsing the language instance to detect an ontology for editing; mapping one or more nodes for the ontology for editing based on the knowledge base; determining whether the mapped nodes are defined or undefined within the knowledge base; calculating a first confidence score based on a number of the defined and undefined mapped nodes; and based on the received language instance and in response to the first confidence score meeting a pre-defined threshold, updating the knowledge base; in response to the first confidence score not meeting the pre-defined threshold, determining a first undefined node within the one or more mapped nodes; inquiring a user as to information regarding the first undefined node; receiving an answer from the user; calculating a second confidence score based on the one or more mapped nodes and the answer; and updating the knowledge base when the second confidence score meets the pre-defined threshold.
A computer program edits knowledge-based ontologies by accepting natural language input to update a knowledge base. It parses the input to identify the relevant ontology, then maps nodes within that ontology based on existing data. The system checks if these nodes are already defined in the knowledge base. A confidence score is calculated based on the proportion of defined versus undefined nodes. If the score exceeds a threshold, the knowledge base is updated automatically. Otherwise, the system asks the user for information about the undefined nodes, calculates a new confidence score based on the user's input, and updates the knowledge base if this new score meets the threshold.
2. The method of claim 1 , further comprising: determining when the answer from the user is one or more of: ambiguous fact, simple fact, or partial fact.
The knowledge-based ontology editor, described previously, categorizes the user's answers about undefined nodes as "ambiguous fact", "simple fact", or "partial fact". This categorization is performed to refine the system's understanding of the new information and guide subsequent interactions with the user, enabling a more precise update of the knowledge base.
3. The method of claim 2 , further comprising: inquiring the user as to information regarding the undefined node in response to the answer being ambiguous fact or partial fact.
Building on the knowledge-based ontology editor that categorizes user input, if the user's answer regarding an undefined node is considered an "ambiguous fact" or a "partial fact," the system will ask the user for further clarification about that same undefined node. This iterative questioning aims to resolve ambiguities and gather complete information to improve the confidence level before updating the knowledge base.
4. The method 3 , further comprising: inquiring a user as to information regarding a second undefined node in response to the answer being ambiguous fact or partial fact.
Continuing from the knowledge-based ontology editor, where the user's answer to an undefined node is ambiguous or partial, the system, after the first inquiry, will inquire the user about a *second*, different undefined node. This allows the system to gather information about multiple unknown aspects of the ontology from the user.
5. The method of claim 1 , further comprising: displaying a nodal relationships among nodes and the language instance to a user in structured form as a graph.
The knowledge-based ontology editor described earlier visually displays the relationships between nodes in the knowledge base and the user's input, showing a structured graph representation of how the natural language relates to the ontology. This visualization helps the user understand how the system interprets their input and facilitates easier review and correction of the proposed changes to the knowledge base.
6. The method of claim 1 , wherein the first confidence score is calculated based on the number of defined and undefined nodes.
In the knowledge-based ontology editor, the "first confidence score" (used to determine if the system has enough information to update the knowledge base) is calculated directly from the ratio of defined and undefined nodes identified during the semantic parsing of the input language instance. Higher numbers of defined nodes increase confidence, while more undefined nodes lower it.
7. The method of claim 1 , wherein the second confidence score is calculated based on the number of defined and undefined nodes.
In the knowledge-based ontology editor, the "second confidence score" (calculated after the system receives user input about undefined nodes) depends on how many defined and undefined nodes remain after incorporating the user's answer. The score reflects the system's confidence in the updated ontology structure after considering the user's provided information.
8. The method of claim 1 , wherein the first confidence score is calculated by comparing the parsed language instance to a pre-loaded knowledge base.
Within the knowledge-based ontology editor, the initial confidence score is determined by comparing the semantically parsed language input to a pre-existing, loaded knowledge base. The comparison assesses how well the language input aligns with established knowledge within the system, providing a baseline confidence level before user interaction.
9. A computer system for knowledge based ontology editing, the computer system comprising: one or more computer processors; one or more computer-readable storage media; program instructions stored on the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising: program instructions to receive a language instance to update a knowledge base, using a computer; program instructions to semantically parse the language instance to detect an ontology for editing; program instructions to map one or more nodes for the ontology for editing based on the knowledge base; program instructions to determine whether the mapped nodes are defined or undefined within the knowledge base; program instructions to calculate a first confidence score based on a number of the defined and undefined mapped nodes; and program instructions to, based on the received language instance and in response to the first confidence score meeting a pre-defined threshold, update the knowledge base; program instructions to, in response to the first confidence score not meeting the pre-defined threshold, determine a first undefined node within the one or more mapped nodes; program instructions to inquire a user as to information regarding the first undefined node; program instructions to receive an answer from the user; program instructions to calculate a second confidence score based on the one or more mapped nodes and the answer; and program instructions to update the knowledge base when the second confidence score meets the pre-defined threshold.
A computer system edits knowledge-based ontologies by accepting natural language input to update a knowledge base. It includes processors, storage, and software that parses the input to identify the relevant ontology, then maps nodes within that ontology based on existing data. The system checks if these nodes are already defined in the knowledge base. A confidence score is calculated based on the proportion of defined versus undefined nodes. If the score exceeds a threshold, the knowledge base is updated automatically. Otherwise, the system asks the user for information about the undefined nodes, calculates a new confidence score based on the user's input, and updates the knowledge base if this new score meets the threshold.
10. The computer system of claim 9 , further comprising: displaying a nodal relationships among nodes and the language instance to a user in structured form as a graph.
The computer system for knowledge-based ontology editing, described previously, also includes a display module. This module visually presents the relationships between nodes in the knowledge base and the user's input as a structured graph. The graph illustrates how the natural language connects to the ontology, helping the user to understand and validate the system's interpretations.
11. A computer program product for knowledge based ontology editing, the computer program product comprising: one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising: receiving a language instance to update a knowledge base, using a computer; semantically parsing the language instance to detect an ontology for editing; mapping one or more nodes for the ontology for editing based on the knowledge base; determining when the mapped nodes are defined or undefined within the knowledge base; calculating a first confidence score based on a number of the defined and undefined mapped nodes; and based on the received language instance and in response to the first confidence score meeting a pre-defined threshold, updating the knowledge base; in response to the first confidence score not meeting the pre-defined threshold, determining a first undefined node within the one or more mapped nodes; inquiring a user as to information regarding the first undefined node; receiving an answer from the user; calculating a second confidence score based on the one or more mapped nodes and the answer; and updating the knowledge base when the second confidence score meets the pre-defined threshold.
A computer program product edits knowledge-based ontologies by accepting natural language input to update a knowledge base. The program parses the input to identify the relevant ontology, then maps nodes within that ontology based on existing data. The system checks if these nodes are already defined in the knowledge base. A confidence score is calculated based on the proportion of defined versus undefined nodes. If the score exceeds a threshold, the knowledge base is updated automatically. Otherwise, the system asks the user for information about the undefined nodes, calculates a new confidence score based on the user's input, and updates the knowledge base if this new score meets the threshold.
12. The computer program product of claim 11 , further comprising determining whether the answer from the user is one or more of ambiguous fact, simple fact, or partial fact.
The computer program product for knowledge-based ontology editing, described previously, categorizes the user's answers about undefined nodes as "ambiguous fact", "simple fact", or "partial fact". This categorization is performed to refine the system's understanding of the new information and guide subsequent interactions with the user, enabling a more precise update of the knowledge base.
13. The computer program product of claim 12 , further comprising inquiring the user as to information regarding the undefined node in response to the answer being ambiguous fact or partial fact.
Building on the knowledge-based ontology editor that categorizes user input, if the user's answer within the computer program product regarding an undefined node is considered an "ambiguous fact" or a "partial fact," the system will ask the user for further clarification about that same undefined node. This iterative questioning aims to resolve ambiguities and gather complete information to improve the confidence level before updating the knowledge base.
14. The computer program product of claim 12 , further comprising inquiring a user as to information regarding a second undefined node in response to the answer being ambiguous fact or partial fact.
Continuing from the knowledge-based ontology editor implemented as a computer program product, where the user's answer to an undefined node is ambiguous or partial, the system, after the first inquiry, will inquire the user about a *second*, different undefined node. This allows the system to gather information about multiple unknown aspects of the ontology from the user.
15. The computer program product of claim 11 , further comprising, displaying a nodal relationships among nodes and the language instance to a user in structured form as a graph.
The knowledge-based ontology editor implemented as a computer program product visually displays the relationships between nodes in the knowledge base and the user's input, showing a structured graph representation of how the natural language relates to the ontology. This visualization helps the user understand how the system interprets their input and facilitates easier review and correction of the proposed changes to the knowledge base.
16. The computer program product of claim 11 , wherein the first confidence score is calculated based on the number of defined and undefined nodes.
In the knowledge-based ontology editor, implemented as a computer program product, the "first confidence score" (used to determine if the system has enough information to update the knowledge base) is calculated directly from the ratio of defined and undefined nodes identified during the semantic parsing of the input language instance. Higher numbers of defined nodes increase confidence, while more undefined nodes lower it.
17. The computer program product of claim 11 , wherein the second confidence score is calculated based on the number of defined and undefined nodes.
In the knowledge-based ontology editor, implemented as a computer program product, the "second confidence score" (calculated after the system receives user input about undefined nodes) depends on how many defined and undefined nodes remain after incorporating the user's answer. The score reflects the system's confidence in the updated ontology structure after considering the user's provided information.
18. The computer program product of claim 11 , wherein the first confidence score is calculated by comparing the parsed language instance to a pre-loaded knowledge base.
Within the knowledge-based ontology editor, implemented as a computer program product, the initial confidence score is determined by comparing the semantically parsed language input to a pre-existing, loaded knowledge base. The comparison assesses how well the language input aligns with established knowledge within the system, providing a baseline confidence level before user interaction.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
November 24, 2015
August 8, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.